NOVEL METHOD TO FIND THE PARAMETER FOR NOISE REMOVAL FROM MULTI-CHANNEL ECG WAVEFORMS

In general, electrocardiogram (ECG) waveforms are affected by noise and artifacts and it is essential to remove the noise in order to support any decision making for specialist. It is very difficult to remove the noise from 12 channel ECG waveforms using standard noise removal methodologies. Removal of the noise from ECG waveforms is majorly classified into two types in signal processing namely Digital filters and Analog filters. Digital filters are more accurate than analog filters because analog filters introduce nonlinear phase shift. Most advanced research digital filters are FIR and IIR.FIR filters are stable as they have non-recursive structure. They give the exact linear phase and efficiently realizable in hardware. The filter response is finite duration. Thus noise removal using FIR digital filter is better option in comparison with IIR digital filter. But it is very difficult to find the cut-off frequency parameter for dynamic multi-channel ECG waveforms using existing traditional methods. So, in this research, newly introduced Multi-Swarm Optimization (MSO) methodology for automatically identifying the cut-off frequency parameter of multichannel ECG waveforms for low-pass filtering is inspecting. Generally, the spectrums of the ECG waveforms are extracted from four classes: normal sinus rhythm, atria fibrillation, arrhythmia and supraventricular. Baseline wander is removed using the Moving Median Filter. A dataset of the extracted features of the ECG spectrums is used to train the MSO. The performance of the MSO with various parameters is investigated. Finally, the MSO-identified cut-off frequency parameter, it’s applied to a Finite Impulse Response (FIR) filter. The resulting signal is evaluated against the original clean and conventional filtered EC